AI’s safety features can be circumvented with poetry, research finds
Poems containing prompts for harmful content prove effective at duping large language models Poetry can be linguistically and structurally unpredictable – and that’s part of its joy. But one man’s joy, it turns out, can be a nightmare for AI models. Those are the recent findings of researchers out of Italy’s Icaro Lab, an initiative […]
AI’s safety features can be circumvented with poetry, research finds Read More »





